Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    patterns related to numerical data and periods/dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numbers followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    graphiques
    -0.43
     zoude
    -0.41
    astéro
    -0.38
    ніципалі
    -0.38
    EDEFAULT
    -0.37
    béco
    -0.36
     Mittelalter
    -0.35
    Karten
    -0.35
     dibujado
    -0.35
     Biôgrafia
    -0.35
    POSITIVE LOGITS
     שוליים
    0.57
     nahilalakip
    0.57
     CreateTagHelper
    0.56
     noDo
    0.54
     '\\;'
    0.53
     okuyayım
    0.52
    ❋
    0.50
    __(/*!
    0.49
    ViewImports
    0.48
    Cyfeiriadau
    0.47
    Act Density 0.001%

    No Known Activations